Skip to content

this is GAN model train on celabA dataset to generate images like celebrity's, it is train on only 10 epochs because training take too much time.

Notifications You must be signed in to change notification settings

Xbectordash/Image_generator-using-GAN

 
 

Repository files navigation

Image Generation App using GAN on Streamlit

This Streamlit app allows you to generate new celebrity faces using a pre-trained Generative Adversarial Network (GAN) model trained on the CelebA dataset. To run the app, follow the steps below:

Images are blurred as it is trained only on 10 epochs

Image 1 Image 1 Image 1

Requirements

To run this app, you need to have the following Python libraries installed:

  • Streamlit (pip install streamlit)
  • TensorFlow (pip install tensorflow)
  • NumPy (pip install numpy)
  • Matplotlib (pip install matplotlib)

Usage

  1. Clone the repository or download the app files.

  2. Make sure you have installed the required dependencies mentioned above.

  3. Open a terminal or command prompt and navigate to the directory containing app.py.

  4. Run the following command to start the Streamlit app:

streamlit run app.py
  1. Once the app is running, open your web browser and go to http://localhost:{PORT}.

  2. Use the slider to select the number of images you want to generate, and click the "Generate" button to see the generated celebrity faces.

License

This project is licensed under the MIT License. See the LICENSE file for more details.

Acknowledgments

  • The CelebA dataset for providing the celebrity face images for training the GAN model.
  • TensorFlow and Keras for their excellent machine learning frameworks.
  • Streamlit for making it easy to build interactive web applications with Python.

Contact

If you have any questions or suggestions, feel free to contact us at kumawatrahul960@gmail.com.

Enjoy generating celebrity faces with GAN on Streamlit!

About

this is GAN model train on celabA dataset to generate images like celebrity's, it is train on only 10 epochs because training take too much time.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.9%
  • Python 0.1%